FedGTA: Topology-aware Averaging for Federated Graph Learning
Summary: FedGTA: a personalized federated graph-learning optimizer that does topology-aware model averaging using local smoothing confidence and mixed neighbor features to preserve graph structure during aggregation. Scales to large graphs (ogbn-papers100M) and outperforms baselines across 12 multi-scale splits. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Xunkai Li
- 2. Yinlin Zhu
- 3. Zhengyu Wu
- 4. Rong-Hua Li
- 5. Wentao Zhang
- 6. Guoren Wang
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,545 | OpenFGL: A Comprehensive Benchmark for Federated Graph Learning | 2025 | VLDB | 4.1945683e-05 |
| 10,936 | NPA: Improving Large-scale Graph Neural Networks with Non-parametric Attention | 2024 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 5,304 | A Scalable AutoML Approach Based on Graph Neural Networks | 2022 | VLDB | 5.5779335e-05 |
| 5,420 | SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization | 2022 | VLDB | 5.5157743e-05 |
Previous
Page 1 / 1
Next